SPEC® CFP2006 Result

Copyright 2006-2014 Standard Performance Evaluation Corporation

Sun Microsystems

Sun SPARC Enterprise M9000

CPU2006 license: 6 Test date: Jul-2008
Test sponsor: Sun Microsystems Hardware Availability: Jul-2008
Tested by: Sun Microsystems Software Availability: Jul-2008
Benchmark results graph
Hardware
CPU Name: SPARC64 VII
CPU Characteristics:
CPU MHz: 2520
FPU: Integrated
CPU(s) enabled: 256 cores, 64 chips, 4 cores/chip, 2 threads/core
CPU(s) orderable: 1 to 16 CMUs; each CMU contains 2 or 4 chips
Primary Cache: 64 KB I + 64 KB D on chip per core
Secondary Cache: 6 MB I+D on chip per chip
L3 Cache: None
Other Cache: None
Memory: 1 TB (512 x 2 GB)
Disk Subsystem: 12 TB RAID 0 Solaris Volume
24 x 500 GB 15000 RPM disk
Stripe interlace size 128Kbytes
Other Hardware: None
Software
Operating System: Solaris 10 5/08 with Patch 137111-03
Compiler: Sun Studio 12 with patches
124867-06, 124861-07, 124863-05, 127000-05
(see patch information below)
Auto Parallel: No
File System: ufs
System State: Default
Base Pointers: 32-bit
Peak Pointers: 32-bit
Other Software: None

Results Table

Benchmark Base Peak
Copies Seconds Ratio Seconds Ratio Seconds Ratio Copies Seconds Ratio Seconds Ratio Seconds Ratio
Results appear in the order in which they were run. Bold underlined text indicates a median measurement.
410.bwaves 511 5485 1270 5337 1300 5338 1300 511 5485 1270 5337 1300 5338 1300
416.gamess 511 4117 2430 4112 2430 4087 2450 255 1671 2990 1671 2990 1670 2990
433.milc 511 6463 726 6464 726 6464 726 255 3215 728 3215 728 3215 728
434.zeusmp 511 1961 2370 1961 2370 1964 2370 511 1961 2370 1961 2370 1964 2370
435.gromacs 511 1091 3340 1114 3270 1103 3310 511 998 3660 980 3720 995 3670
436.cactusADM 511 2264 2700 2255 2710 2255 2710 255 1000 3050 1000 3050 1001 3050
437.leslie3d 511 4303 1120 4300 1120 4327 1110 255 2059 1160 2057 1170 2058 1160
444.namd 511 1054 3890 1042 3930 1042 3930 511 1034 3960 1035 3960 1041 3940
447.dealII 511 1651 3540 1654 3530 1649 3550 511 1602 3650 1587 3680 1587 3680
450.soplex 511 4964 859 4928 865 4940 863 255 2227 955 2197 968 2198 968
453.povray 511 889 3060 827 3290 921 2950 511 605 4490 594 4580 589 4620
454.calculix 511 1094 3860 1094 3850 1093 3860 511 1062 3970 1063 3970 1063 3970
459.GemsFDTD 511 6599 822 6598 822 6595 822 255 3185 850 3185 849 3186 849
465.tonto 511 1944 2590 1943 2590 1934 2600 255 878 2860 876 2870 876 2860
470.lbm 511 6357 1100 6358 1100 6360 1100 255 3136 1120 3138 1120 3138 1120
481.wrf 511 3200 1780 3197 1790 3204 1780 255 1522 1870 1519 1880 1520 1870
482.sphinx3 511 8342 1190 8403 1190 8377 1190 255 4139 1200 4137 1200 4131 1200

Compiler Invocation Notes

Sun Studio compiler patches are available at
    http://developers.sun.com/sunstudio/downloads/patches/ss12_patches.jsp

Submit Notes


Processes were assigned to specific processors using 'pbind' commands.  The
config file option 'submit' was used, along with a list of processors in the
'BIND' variable, to generate the pbind commands.  (For details, please see
the config file.)

Operating System Notes


Environment Variable Settings:

export LD_PRELOAD=mpss.so.1:madv.so.1
export MPSSHEAP=4MB
export MPSSSTACK=4MB
    Requests system to use 4 MB pages when possible.
export MADV access_lwp
    access_lwp requests that the next light weight process to touch
    the specified address range will access it most heavily.
ulimit -s 131072 was used to limit the space consumed
    by the stack (making more space available for the heap)

System Tunables (/etc/system parameters):

autoup=200
    Causes pages older than the listed number of seconds to
    be written by fsflush.
lpg_alloc_prefer=1
    Set lgroup page allocation to strongly prefer local pages

Other System Settings:

The webconsole service was turned off using
    svcadm disable webconsole

The SPEC toolset was bound to processors 1-511 using processor sets:
    psrset -c 1-511
    psrset -e 1 ksh

Platform Notes


Memory is 8-way interleaved by filling all slots with
the same capacity DIMMs.

This result is measured on a Sun SPARC Enterprise M9000 Server.
Note that the Sun SPARC Enterprise M9000 and Fujitsu SPARC Enterprise
M9000 are electrically equivalent.

Base Compiler Invocation

C benchmarks:

 cc 

C++ benchmarks:

 CC 

Fortran benchmarks:

 f90 

Benchmarks using both Fortran and C:

 cc   f90 

Base Optimization Flags

C benchmarks:

 -fast   -xipo=2   -xpagesize=4M   -xprefetch_level=1   -fma=fused   -xalias_level=std   -xprefetch_auto_type=indirect_array_access   -ll2amm 

C++ benchmarks:

 -library=stlport4   -fast   -xipo=2   -xpagesize=4M   -xprefetch_level=1   -fma=fused   -xalias_level=compatible   -ll2amm 

Fortran benchmarks:

 -fast   -xipo=2   -xpagesize=4M   -xprefetch_level=1   -fma=fused   -ll2amm 

Benchmarks using both Fortran and C:

 -fast(cc)   -fast(f90)   -xipo=2   -xpagesize=4M   -xprefetch_level=1   -fma=fused   -xalias_level=std   -xprefetch_auto_type=indirect_array_access   -ll2amm 

Peak Compiler Invocation

C benchmarks:

 cc 

C++ benchmarks:

 CC 

Fortran benchmarks:

 f90 

Benchmarks using both Fortran and C:

 cc   f90 

Peak Optimization Flags

C benchmarks:

433.milc:  -fast   -xipo=2   -xpagesize=4M   -fma=fused   -xalias_level=strong   -xprefetch_level=2   -xprefetch_auto_type=indirect_array_access   -xprefetch=latx:5   -ll2amm 
470.lbm:  -xprofile=collect:./feedback(pass 1)   -xprofile=use:./feedback(pass 2)   -fast   -xrestrict   -xipo=2   -xprefetch_level=2   -xarch=v8plusb   -ll2amm 
482.sphinx3:  -xprofile=collect:./feedback(pass 1)   -xprofile=use:./feedback(pass 2)   -fast   -xipo=2   -xpagesize=4M   -fma=fused   -xinline=   -xalias_level=strong   -xprefetch_level=2   -lfast   -ll2amm 

C++ benchmarks:

444.namd:  -library=stlport4   -fast   -xipo=2   -xpagesize=4M   -fma=fused   -xdepend   -xalias_level=compatible   -xprefetch_level=1   -xprefetch=latx:0.5   -ll2amm 
447.dealII:  -library=stlport4   -xprofile=collect:./feedback(pass 1)   -xprofile=use:./feedback(pass 2)   -fast   -xipo=2   -xpagesize=4M   -fma=fused   -xdepend   -xalias_level=compatible   -xrestrict   -xprefetch=no   -ll2amm 
450.soplex:  -library=stlport4   -xprofile=collect:./feedback(pass 1)   -xprofile=use:./feedback(pass 2)   -fast   -xipo=2   -xpagesize=4M   -fma=fused   -xdepend   -xalias_level=compatible   -fsimple=0   -xrestrict   -xprefetch=no   -ll2amm 
453.povray:  -library=stlport4   -xprofile=collect:./feedback(pass 1)   -xprofile=use:./feedback(pass 2)   -fast   -xipo=2   -xpagesize=4M   -fma=fused   -xdepend   -xalias_level=compatible   -xprefetch=latx:5.0   -ll2amm 

Fortran benchmarks:

410.bwaves:  basepeak = yes 
416.gamess:  -xprofile=collect:./feedback(pass 1)   -xprofile=use:./feedback(pass 2)   -fast   -xipo=2   -xpagesize=4M   -fma=fused   -xprefetch_level=1   -ll2amm 
434.zeusmp:  basepeak = yes 
437.leslie3d:  -fast   -xipo=2   -xpagesize=4M   -fma=fused   -xprefetch=latx:5.0   -ll2amm 
459.GemsFDTD:  -fast   -xipo=2   -xpagesize=4M   -fma=fused   -fsimple=1   -xprefetch=no   -ll2amm 
465.tonto:  -fast   -xipo=2   -xpagesize=4M   -fma=fused   -xprefetch=no   -lfast   -ll2amm 

Benchmarks using both Fortran and C:

435.gromacs:  -xprofile=collect:./feedback(pass 1)   -xprofile=use:./feedback(pass 2)   -fast(cc)   -fast(f90)   -xipo=2   -xpagesize=4M   -fma=fused   -fsimple=0   -xprefetch=latx:0.5   -xarch=generic   -xchip=generic 
436.cactusADM:  -fast(cc)   -fast(f90)   -xipo=2   -xpagesize=4M   -fma=fused   -ll2amm 
454.calculix:  -fast(cc)   -fast(f90)   -xipo=2   -xpagesize=4M   -fma=fused   -xprefetch=latx:3.0   -ll2amm 
481.wrf:  -xprofile=collect:./feedback(pass 1)   -xprofile=use:./feedback(pass 2)   -fast(cc)   -fast(f90)   -xipo=2   -xpagesize=4M   -fma=fused   -xprefetch=no   -ll2amm 

The flags file that was used to format this result can be browsed at
http://www.spec.org/cpu2006/flags/Sun-Solaris-Studio12-and-gccfss4.2.20090713.00.html.

You can also download the XML flags source by saving the following link:
http://www.spec.org/cpu2006/flags/Sun-Solaris-Studio12-and-gccfss4.2.20090713.00.xml.